Estimating leaf mass per area and equivalent water thickness based on leaf optical properties: Potential and limitations of physical modeling and machine learning

• Published in: Remote sensing of environment Vol. 231; p. 110959
• Main Authors: Féret, J.-B., le Maire, G., Jay, S., Berveiller, D., Bendoula, R., Hmimina, G., Cheraiet, A., Oliveira, J.C., Ponzoni, F.J., Solanki, T., de Boissieu, F., Chave, J., Nouvellon, Y., Porcar-Castell, A., Proisy, C., Soudani, K., Gastellu-Etchegorry, J.-P., Lefèvre-Fonollosa, M.-J.
• Format: Journal Article
• Language: English
• Published: New York Elsevier Inc 15.09.2019; Elsevier BV; Elsevier
• Subjects: Algorithms; Artificial intelligence; Biodiversity and Ecology; Biophysical properties; data collection; Domains; Ecological function; Ecosystem management; Ecosystems; Environmental Sciences; Equivalence; Estimation errors; EWT; Iterative methods; leaf mass; Leaf spectroscopy; Learning algorithms; Leaves; LMA; Machine learning; near-infrared spectroscopy; Optical properties; Optimization; Radiative transfer model; Reflectance; Regression analysis; Regression models; remote sensing; Risk management; Short wave radiation; Spectra; Statistical methods; Support vector machine; Support vector machines; Thickness; Training; Transmittance; Vegetation; Leaf spectroscopy; LMA; Radiative transfer model; EWT; Biophysical properties; Vegetation; Support vector machine; OPTICAL PROPERTIES; MODELING; MACHINE LEARNING; ECOSYSTEM; LEAF; RISK MANAGEMENT
• DOI: 10.1016/j.rse.2018.11.002
• ISSN: 0034-4257

Leaf mass per area (LMA) and leaf equivalent water thickness (EWT) are key leaf functional traits providing information for many applications including ecosystem functioning modeling and fire risk management. In this paper, we investigate two common conclusions generally made for LMA and EWT estimation based on leaf optical properties in the near-infrared (NIR) and shortwave infrared (SWIR) domains: (1) physically-based approaches estimate EWT accurately and LMA poorly, while (2) statistically-based and machine learning (ML) methods provide accurate estimates of both LMA and EWT. Using six experimental datasets including broadleaf species samples of >150 species collected over tropical, temperate and boreal ecosystems, we compared the performances of a physically-based method (PROSPECT model inversion) and a ML algorithm (support vector machine regression, SVM) to infer EWT and LMA based on leaf reflectance and transmittance. We assessed several merit functions to invert PROSPECT based on iterative optimization and investigated the spectral domain to be used for optimal estimation of LMA and EWT. We also tested several strategies to select the training samples used by the SVM, in order to investigate the generalization ability of the derived regression models. We evidenced that using spectral information from 1700 to 2400 nm leads to strong improvement in the estimation of EWT and LMA when performing a PROSPECT inversion, decreasing the LMA and EWT estimation errors by 55% and 33%, respectively. The comparison of various sampling strategies for the training set used with SVM suggests that regression models show limited generalization ability, particularly when the regression model is applied on data fully independent from the training set. Finally, our results demonstrate that, when using an appropriate spectral domain, the PROSPECT inversion outperforms SVM trained with experimental data for the estimation of EWT and LMA. Thus we recommend that estimation of LMA and EWT based on leaf optical properties should be physically-based using inversion of reflectance and transmittance measurements on the 1700 to 2400 nm spectral range. •Limitations of physical modeling for the estimation of LMA need to be understood.•Species samples of >150 boreal, temperate and tropical species are studied.•Performance of PROSPECT inversion is reduced when near infrared is used.•Machine learning trained with experimental data shows poor generalization ability.•LMA and EWT can be accurately estimated with PROSPECT inverted from 1700 to 2400 nm.